# Anthropic Protein Design evaluation (Protein Design)

> Generates novel protein sequences under family, topology, globularity, and structural-motif constraints.

Canonical page: https://benchlm.ai/benchmarks/proteindesign

- Category: [Knowledge](/knowledge)
- Last updated: September 22, 2026

## About Protein Design

- Year: 2026
- Tasks: Constrained protein-sequence design tasks
- Format: Composite score
- Difficulty: Computational protein design
- Paper: [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf)

Section 8.17.4 reports a composite of constraint satisfaction, folding confidence, and sequence novelty without tool access.

Protein Design is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (2 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 60.2% |
| 2 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 42.5% |

## FAQ

### What does Protein Design measure?

Generates novel protein sequences under family, topology, globularity, and structural-motif constraints.

### Which model scores highest on Protein Design?

Claude Opus 5.5 by Anthropic currently leads with a score of 60.2% on Protein Design.

### How many models are evaluated on Protein Design?

2 AI models have been evaluated on Protein Design on BenchLM.

### Does Protein Design affect BenchLM's overall score?

Not directly. Protein Design is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on Protein Design

- [Claude Opus 5.5 vs Claude Opus 5](/compare/claude-opus-5-vs-claude-opus-5-5)